© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7765
    Prev
    Next
    INDEX
    Explanations

    unit related phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heets
    -0.07
    жин
    -0.07
    ê°Ģ
    -0.07
    edel
    -0.07
    ematik
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    tera
    -0.07
    eson
    -0.07
    ftware
    -0.07
    ythe
    -0.07
    POSITIVE LOGITS
    itarian
    0.10
    ä¹İ
    0.10
    ary
    0.09
    ized
    0.09
    errupted
    0.09
    IALIZED
    0.09
    ĺ
    0.09
    æŶéĹ´åĨħ
    0.08
    leman
    0.08
    Ñģловно
    0.08
    Activations Density 0.046%

    No Known Activations